from sagemaker.huggingface import HuggingFaceModel

# create Hugging Face Model Class and deploy it as SageMaker endpoint
huggingface_model = HuggingFaceModel(...).deploy()

pip install sagemaker --upgrade

import sagemaker
sess = sagemaker.Session()
role = sagemaker.get_execution_role()

import sagemaker
import boto3

iam_client = boto3.client('iam')
role = iam_client.get_role(RoleName='role-name-of-your-iam-role-with-right-permissions')['Role']['Arn']
sess = sagemaker.Session()

from sagemaker.huggingface import HuggingFace

############ pseudo code start ############

# create Hugging Face Estimator for training
huggingface_estimator = HuggingFace(....)

# start the train job with our uploaded datasets as input
huggingface_estimator.fit(...)

############ pseudo code end ############

# deploy model to SageMaker Inference
predictor = hf_estimator.deploy(initial_instance_count=1, instance_type="ml.m5.xlarge")

# example request: you always need to define "inputs"
data = {
   "inputs": "Camera - You are awarded a SiPix Digital Camera! call 09061221066 from landline. Delivery within 28 days."
}

# request
predictor.predict(data)

# delete endpoint
predictor.delete_endpoint()

from sagemaker.huggingface.model import HuggingFaceModel

# create Hugging Face Model Class
huggingface_model = HuggingFaceModel(
   model_data="s3://models/my-bert-model/model.tar.gz",  # path to your trained SageMaker model
   role=role,                                            # IAM role with permissions to create an endpoint
   transformers_version="4.26",                           # Transformers version used
   pytorch_version="1.13",                                # PyTorch version used
   py_version='py39',                                    # Python version used
)

# deploy model to SageMaker Inference
predictor = huggingface_model.deploy(
   initial_instance_count=1,
   instance_type="ml.m5.xlarge"
)

# example request: you always need to define "inputs"
data = {
   "inputs": "Camera - You are awarded a SiPix Digital Camera! call 09061221066 from landline. Delivery within 28 days."
}

# request
predictor.predict(data)

# delete endpoint
predictor.delete_endpoint()

model.tar.gz/
|- pytorch_model.bin
|- vocab.txt
|- tokenizer_config.json
|- config.json
|- special_tokens_map.json

git lfs install
git clone git@hf.co:{repository}

cd {repository}
tar zcvf model.tar.gz *

aws s3 cp model.tar.gz <s3://{my-s3-path}>

from sagemaker.huggingface.model import HuggingFaceModel

# Hub model configuration <https://huggingface.co/models>
hub = {
  'HF_MODEL_ID':'distilbert-base-uncased-distilled-squad', # model_id from hf.co/models
  'HF_TASK':'question-answering'                           # NLP task you want to use for predictions
}

# create Hugging Face Model Class
huggingface_model = HuggingFaceModel(
   env=hub,                                                # configuration for loading model from Hub
   role=role,                                              # IAM role with permissions to create an endpoint
   transformers_version="4.26",                             # Transformers version used
   pytorch_version="1.13",                                  # PyTorch version used
   py_version='py39',                                      # Python version used
)

# deploy model to SageMaker Inference
predictor = huggingface_model.deploy(
   initial_instance_count=1,
   instance_type="ml.m5.xlarge"
)

# example request: you always need to define "inputs"
data = {
"inputs": {
	"question": "What is used for inference?",
	"context": "My Name is Philipp and I live in Nuremberg. This model is used with sagemaker for inference."
	}
}

# request
predictor.predict(data)

# delete endpoint
predictor.delete_endpoint()

batch_job = huggingface_estimator.transformer(
    instance_count=1,
    instance_type='ml.p3.2xlarge',
    strategy='SingleRecord')


batch_job.transform(
    data='s3://s3-uri-to-batch-data',
    content_type='application/json',    
    split_type='Line')

from sagemaker.huggingface.model import HuggingFaceModel

# Hub model configuration <https://huggingface.co/models>
hub = {
	'HF_MODEL_ID':'distilbert/distilbert-base-uncased-finetuned-sst-2-english',
	'HF_TASK':'text-classification'
}

# create Hugging Face Model Class
huggingface_model = HuggingFaceModel(
   env=hub,                                                # configuration for loading model from Hub
   role=role,                                              # IAM role with permissions to create an endpoint
   transformers_version="4.26",                             # Transformers version used
   pytorch_version="1.13",                                  # PyTorch version used
   py_version='py39',                                      # Python version used
)

# create transformer to run a batch job
batch_job = huggingface_model.transformer(
    instance_count=1,
    instance_type='ml.p3.2xlarge',
    strategy='SingleRecord'
)

# starts batch transform job and uses S3 data as input
batch_job.transform(
    data='s3://sagemaker-s3-demo-test/samples/input.jsonl',
    content_type='application/json',    
    split_type='Line'
)

{"inputs":"this movie is terrible"}
{"inputs":"this movie is amazing"}
{"inputs":"SageMaker is pretty cool"}
{"inputs":"SageMaker is pretty cool"}
{"inputs":"this movie is terrible"}
{"inputs":"this movie is amazing"}

pip install sagemaker>=2.231.0

import sagemaker
from sagemaker.huggingface import HuggingFaceModel, get_huggingface_llm_image_uri
import time

sagemaker_session = sagemaker.Session()
region = sagemaker_session.boto_region_name
role = sagemaker.get_execution_role()

image_uri = get_huggingface_llm_image_uri(
  backend="huggingface",
  region=region
)

model_name = "llama-3-1-8b-instruct" + time.strftime("%Y-%m-%d-%H-%M-%S", time.gmtime())

hub = {
    'HF_MODEL_ID':'meta-llama/Llama-3.1-8B-Instruct',
    'SM_NUM_GPUS':'1',
	'HUGGING_FACE_HUB_TOKEN': '<REPLACE WITH YOUR TOKEN>',
}

assert hub['HUGGING_FACE_HUB_TOKEN'] != '<REPLACE WITH YOUR TOKEN>', "You have to provide a token."


model = HuggingFaceModel(
    name=model_name,
    env=hub,
    role=role,
    image_uri=image_uri
)

predictor = model.deploy(
  initial_instance_count=1,
  instance_type="ml.g5.2xlarge",
  endpoint_name=model_name
)

input_data = {
  "inputs": "The diamondback terrapin was the first reptile to",
  "parameters": {
    "do_sample": True,
    "max_new_tokens": 100,
    "temperature": 0.7,
    "watermark": True
  }
}

predictor.predict(input_data)

[{'generated_text': 'The diamondback terrapin was the first reptile to make the list, followed by the American alligator, the American crocodile, and the American box turtle. The polecat, a ferret-like animal, and the skunk rounded out the list, both having gained their slots because they have proven to be particularly dangerous to humans.\n\nCalifornians also seemed to appreciate the new list, judging by the comments left after the election.\n\n“This is fantastic,” one commenter declared.\n\n“California is a very'}]

predictor.delete_model()
predictor.delete_endpoint()

model.tar.gz/
|- pytorch_model.bin
|- ....
|- code/
  |- inference.py
  |- requirements.txt 

from sagemaker_huggingface_inference_toolkit import decoder_encoder

def model_fn(model_dir):
    # implement custom code to load the model
    loaded_model = ...
    
    return loaded_model 

def input_fn(input_data, content_type):
    # decode the input data  (e.g. JSON string -> dict)
    data = decoder_encoder.decode(input_data, content_type)
    return data

def predict_fn(data, model):
    # call your custom model with the data
    outputs = model(data , ... )
    return predictions

def output_fn(prediction, accept):
    # convert the model output to the desired output format (e.g. dict -> JSON string)
    response = decoder_encoder.encode(prediction, accept)
    return response

from sagemaker_huggingface_inference_toolkit import decoder_encoder

def model_fn(model_dir):
    # implement custom code to load the model
    loaded_model = ...
    
    return loaded_model 

def transform_fn(model, input_data, content_type, accept):
     # decode the input data (e.g. JSON string -> dict)
    data = decoder_encoder.decode(input_data, content_type)

    # call your custom model with the data
    outputs = model(data , ... ) 

    # convert the model output to the desired output format (e.g. dict -> JSON string)
    response = decoder_encoder.encode(output, accept)

    return response